Reconstruction of the wavefront phase with the use of a complex neural network
S.V. Artyshchenko1, P.A. Golovinski1,2, R.A. Chernov1
1Voronezh State University of Architecture and Civil Engineering, 394006, Voronezh, ul. 20-letija Oktjabrja, 84
2Moscow Institute of Physics and Technology, per. Institutskiy, 9, Moscow Region, Dolgoprudnyiy, 141700, Russia
Keywords: Shack-Hartmann sensor, wavefront reconstruction, turbulent atmosphere, complex neural network, genetic algorithm
Abstract
We considered the process of wavefront reconstruction, which is based on the use of Shack-Hartmann sensor and complex-valued artificial neural network. The pixel positions are mapped on a complex plane. The process of phase reconstruction has been tested with the help of the distorted wavefront, which was obtained in the framework of a statistical model for a turbulent atmosphere. The learning of the network is based on a genetic algorithm. The process has the fast convergence, resistance to the local errors, and dynamic adaptability.
|
